Personalization in Goal-Oriented Dialog

By Chaitanya K. Joshi, Fei Mi, Boi Faltings. 2017

105 citations recorded by the source corpus.

The main goal of modeling human conversation is to create agents which can interact with people in both open-ended and goal-oriented scenarios. End-to-end trained neural dialog systems are an important line of research for such generalized dialog models as they do not resort to any situation-specific handcrafting of rules. However, incorporating personalization into such systems is a largely unexplored topic as there are no existing corpora to facilitate such work. In this paper, we present a new dataset of goal-oriented dialogs which are influenced by speaker profiles attached to them. We analyze the shortcomings of an existing end-to-end dialog system based on Memory Networks and propose modifications to the architecture which enable personalization. We also investigate personalization in dialog as a multi-task learning problem, and show that a single model which shares features among various profiles outperforms separate models for each profile.

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

Personalizing Dialogue Agents: I have a dog, do you have pets too? (2018, background): “In the case of goal-oriented dialogue some work has focused on the agent being aware of the human’s proﬁle and adjusting the dialogue accordingly, but without a personality to the agent itself (Lucas et al., 2009; Joshi et al., 2017).”
Training Millions of Personalized Dialogue Agents (2018, background): “Other classic strategies include extracting explicit variables from structured knowledge bases or other symbolic sources as in (Ghazvininejad et al., 2017; Joshi et al., 2017; Young et al., 2017).”
Challenges in Building Intelligent Open-domain Dialog Systems (2019, background): “[31] developed a personalized version of the bAbI dialoge dataset [6] by associating each goal-oriented dialog with user traits such as gender, age, and favorite foods.”
A Survey on Conversational Recommender Systems (2020, methodology): “It consists of three datasets (training, development and testing), each comprising 6,000 dialogues [63].”
Learning Personalized End-to-End Goal-Oriented Dialog (2018, methodology): “Following Joshi, Mi, and Faltings (2017), we report per-response accuracy across all models and tasks on the personalized bAbI dataset in Table 1.”
You Impress Me: Dialogue Generation via Mutual Persona Perception (2020, background): “Personalization in goal-oriented dialogue systems has also received some attention (Joshi et al., 2017; Luo et al., 2019).”
Condition Aware and Revise Transformer for Question Answering (2020, methodology): “CAR-Transformer is compared with supervised embeddings and Memory Network [29] as in [14].”
Personalizing Dialogue Agents via Meta-Learning (2019, background): “Several works improved on the initial baselines with various methodologies (Kulikov et al., 2018; Yavuz et al.; Hancock et al., 2019; Lucas et al., 2009; Joshi et al., 2017; Zemlyanskiy and Sha, 2018; Gao et al., 2018).”
Alternating Recurrent Dialog Model with Large-scale Pre-trained Language Models (2019, background): “Other researchers model persona information to generate language with different speaking styles (Li et al., 2016; Joshi et al., 2017).”